feat(ci): P2-6 新增CI健康度每日巡检定时任务

每天北京时间早上9点自动执行： - 统计最近30条CI run的成功率 - 区分基础设施vs业务代码失败 - 有失败时自动发送飞书卡片报告到项目群 - 全部通过时静默，不打扰对应脚本: scripts/ci/ci_health_report.py
2026-07-20 21:41:30 +08:00
parent 37033b66a9
commit ccbbd12a7f
1 changed files with 81 additions and 0 deletions
@@ -0,0 +1,81 @@
+name: CI Health Daily Report
+
+on:
+  schedule:
+    - cron: '0 1 * * *'  # UTC 01:00 = 北京时间 09:00
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  ci-health-report:
+    name: CI健康度每日巡检
+    runs-on: saas
+    timeout-minutes: 10
+
+    steps:
+    - name: Checkout code
+      shell: sh
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      run: |
+        set -eu
+        python3 - <<'PY'
+        import io, os, tarfile, time, urllib.request, urllib.error
+        url = f"{os.environ['GITHUB_API_URL']}/repos/{os.environ['GITHUB_REPOSITORY']}/archive/{os.environ['GITHUB_SHA']}.tar.gz"
+        request = urllib.request.Request(url, headers={"Authorization": f"token {os.environ['GITHUB_TOKEN']}"})
+        last_err = None
+        for attempt in range(5):
+            try:
+                with urllib.request.urlopen(request, timeout=120) as response:
+                    archive = response.read()
+                break
+            except urllib.error.HTTPError as e:
+                last_err = e
+                if e.code >= 500 and attempt < 4:
+                    wait = 2 ** attempt
+                    print(f"Checkout HTTP {e.code}, retrying in {wait}s (attempt {attempt+1}/5)...")
+                    time.sleep(wait)
+                    continue
+                raise
+            except Exception as e:
+                last_err = e
+                if attempt < 4:
+                    wait = 2 ** attempt
+                    print(f"Checkout error: {e}, retrying in {wait}s (attempt {attempt+1}/5)...")
+                    time.sleep(wait)
+                    continue
+                raise
+        else:
+            raise last_err
+        with tarfile.open(fileobj=io.BytesIO(archive), mode='r:gz') as tar:
+            root_prefix = tar.getmembers()[0].name.split('/', 1)[0] + '/'
+            for member in tar.getmembers():
+                name = member.name
+                if name == root_prefix[:-1]:
+                    continue
+                if name.startswith(root_prefix):
+                    member.name = name[len(root_prefix):]
+                if member.name:
+                    tar.extract(member, '.')
+        PY
+
+    - name: Run CI health check and report
+      shell: sh
+      env:
+        GITEA_TOKEN: ${{ github.token }}
+        CI_NOTIFY_WEBHOOK: ${{ secrets.CI_NOTIFY_WEBHOOK }}
+      run: |
+        set +e
+        echo "=== CI健康度每日巡检 ==="
+        echo "时间: $(date '+%Y-%m-%d %H:%M:%S')"
+        echo ""
+
+        python3 scripts/ci/ci_health_report.py --limit 30
+        EXIT_CODE=$?
+
+        echo ""
+        echo "巡检完成 (exit code: $EXIT_CODE)"
+        # 永远成功，不影响CI状态（通知失败不应该标红）
+        exit 0